This is the result of Anthropic and others focusing on imaginary threats about things the model cannot realistically do - such as engineer bio weapons.
To guard against the imaginary threats, they compromise real use cases.
To guard against the imaginary threats, they compromise real use cases.
As a rather hilarious and really annoying related issue - I have a real use where the application I'm working on is partially monitoring/analyzing the bloodlines of some rather specific/ancient mammals used in competition and... well.. it doesn't like terms like "breeders" and "breeding"